Conflict evidence fusion method based on similarity and false degree

Abstract

The invention discloses a conflict evidence fusion method based on similarity and false degree. The method comprises the steps of obtaining fault diagnosis information of a power system, conversion into evidence information, the relationship between the maximum value and the minimum value of the basic probability allocation values of all the same focal elements among the evidences is utilized; defining the similarity and the false degree between new evidences, combining the similarity and the false degree with the relation of evidence weight coefficients and referring to a Murphy method to carry out correction again, finally fusing the corrected evidences one by one by adopting a Dempster combination rule, and outputting a final result. According to the invention, the similarity and falsedegree between evidences are comprehensively considered; the mutual support degree of each evidence for the same proposition is measured by utilizing the similarity of the basic probability assignmentof all the same focal elements in the evidences; and comprehensively considering the mutual support degree of all focal elements among the evidences and the false degree for measuring the conflict degree of the fused evidences, and determining the weight coefficient of the fused evidences together, thereby realizing quick and accurate processing of power system fault diagnosis.

Description

technical field [0001] The present invention relates to the technical field of multi-source information fusion, in particular to a method for fusion of conflict evidence based on similarity and falsity. Background technique [0002] The power system fault diagnosis uses the alarm information generated after the fault diagnosis to timely and effectively determine the fault component, and provides auxiliary decision-making for the dispatcher to quickly identify and clear the fault, so as to ensure the safety of the power system operation. In actual fault diagnosis, due to the complexity of the equipment itself and the instability of the operating environment, information is often lost, resulting in incomplete information. Only relying on the information provided by a single sensor is prone to misjudgment and endangers the safety of the power system. With the increase of sensor categories, the development of computer technology, information processing, and pattern recognition t...

AI Technical Summary

Problems solved by technology

[0004] The Dempster combination rule is the core of the D-S evidence theory, but in the practical application of the Dempster combination rule, it is often faced with dealing with various uncertain conflicting information, especially when solving the fusion of low-confidence and high-conflict evidence, conclusions

Images